Hello, I'm

Sandra Kimiring

Machine Learning Engineer | Data Scientist

I build end-to-end machine learning systems, data products, and analytics solutions - from exploration to deployment with a focus on real-world impact.

Sandra Kimiring
Scroll

Building with Purpose

I'm a Machine Learning Engineer and Data Scientist based in Nairobi, Kenya, passionate about creating intelligent systems that solve real problems. My work spans the full ML lifecycle - from data exploration and feature engineering to model development, deployment, and monitoring.

I believe in the power of data and AI to drive meaningful change, especially in African contexts, where responsible and thoughtful AI can make a significant difference.

Education

BSc Data Science & Analytics JKUAT (2022–2026)

Interests

  • Building production-ready machine learning systems
  • Personalization and intelligent information retrieval
  • Language-driven AI systems and human–AI interaction
  • Data-informed decision support
  • Responsible, trustworthy, and ethical AI
  • Technology for social impact and emerging markets

Tech Stack

Core Languages

Python SQL / PostgreSQL MySQL R GitHub

Machine Learning & AI

Scikit-learn PyTorch TensorFlow Keras Hugging Face SentenceTransformers FAISS MLflow Weights & Biases

Data & Analytics

Pandas NumPy Power BI Tableau Excel

Deployment & Systems

Docker FastAPI Streamlit AWS Git n8n Redis Terraform

Agentic & AI Systems

LangChain OpenAI API Anthropic API RAG Systems

What I've Built

A selection of machine learning systems, analytics dashboards, and exploratory AI work.

🧠 Machine Learning Projects

Netflix Hybrid Recommendation System

End-to-end hybrid recommender combining collaborative filtering (SVD) with content-based methods (TF-IDF), served via FastAPI.

SVD TF-IDF FastAPI
Hybrid approach API deployment

Diabetes Prediction System

End-to-end ML pipeline for diabetes prediction with comprehensive feature engineering, model comparison, and production API deployment.

Scikit-learn Feature Engineering FastAPI
Model comparison End-to-end pipeline

Nairobi House Price Prediction

Regression modeling on real Kenyan real estate data, featuring location-based feature engineering and market insights.

Regression Feature Engineering Pandas
Real Kenyan dataset Local context

Time Series Forecasting with LSTM

Bitcoin price forecasting using Long Short-Term Memory networks with interactive Streamlit visualization dashboard.

LSTM TensorFlow Streamlit
Deep learning Interactive viz

NLP Sentiment Analysis Pipeline

Text classification pipeline comparing classical ML approaches with transformer-based models for sentiment analysis.

NLP Transformers Scikit-learn
Text preprocessing Model comparison

Computer Vision Experiments

Exploratory projects in transfer learning, image segmentation, and object detection — building foundational CV skills.

Transfer Learning PyTorch OpenCV
Image segmentation Object detection

📊 Data Analytics & Visualization

M-Pesa Transaction Analysis

Analyzed M-Pesa transaction data from June 2023 to June 2024 using Power BI. Transformed and cleaned data to uncover key transaction categories, spending habits, and financial trends over the period.

Power BI Data Cleaning Financial Analysis
Spending patterns Trend analysis

Data Analytics Projects

Selected data analytics projects showcasing insights from entertainment and retail data. Includes interactive dashboards and demographic analyses to uncover trends, patterns, and actionable insights.

Tableau Excel Kaggle Data Visualization Customer Insights
Interactive dashboards Trend analysis Business insights

Power BI Interactive Dashboards

Collection of interactive dashboards built with Power BI to visualize and analyze complex datasets. Offers actionable insights and supports data-driven decision-making through engaging visuals.

Power BI DAX Business Intelligence
Interactive visuals Decision support

Tableau Interactive Dashboards

Dynamic dashboards created with Tableau for exploring and understanding complex data. Features intuitive navigation and compelling visualizations for storytelling with data.

Tableau Data Storytelling Visual Analytics
Data storytelling Dynamic visuals

Thoughts & Involvement

✍️ Writing

Originally published on Medium.

Trustworthy AI for Government Loan Approvals in Kenya

Exploring fairness, transparency, and accountability in ML systems for financial inclusion.

Read on Medium →

Building a Hybrid Recommender System (Netflix)

A deep dive into combining collaborative and content-based filtering approaches.

Read on Medium →

Time Series Forecasting with LSTM

Practical guide to implementing LSTM networks for temporal predictions.

Read on Medium →

Encoders and Decoders in Transformer Architecture

Breaking down the attention mechanism and transformer components.

Read on Medium →

Predicting Nairobi House Prices

Applied ML on local real estate data with Kenyan market insights.

Read on Medium →

Precision, Recall, F1-score & Confusion Matrix

A clear guide to classification metrics that actually makes sense.

Read on Medium →

Hyperparameter Tuning Guide

Practical strategies for optimizing model performance systematically.

Read on Medium →

Data Cleaning vs Data Transformation

Understanding the distinction and when to apply each technique.

Read on Medium →

🔬 Research

Applied research interests in trustworthy AI, recommender systems, and ML systems for African contexts. Exploring how responsible machine learning can address local challenges in health, finance, and governance.

Publications forthcoming.

🌍 Community & Events

Accepted

Deep Learning Indaba

Africa's premier machine learning gathering — connecting with researchers and practitioners across the continent.

Phoenix Analytics Agentic AI Hackathon

Won the hackathon building agentic AI solutions. View on LinkedIn →

Leadership & Volunteering

Contributing to tech communities through mentorship and knowledge sharing initiatives.

Let's Connect

Open to opportunities, collaborations, and conversations about ML, data, and tech for good.